检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

7,070 篇 会议
48 篇 期刊文献
39 册 图书

馆藏范围

7,157 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,912 篇 工学
- 4,098 篇 计算机科学与技术...
- 2,521 篇 软件工程
- 1,046 篇 信息与通信工程
- 789 篇 控制科学与工程
- 663 篇 生物工程
- 640 篇 电气工程
- 424 篇 生物医学工程（可授...
- 285 篇 交通运输工程
- 281 篇 机械工程
- 226 篇 仪器科学与技术
- 226 篇 安全科学与工程
- 206 篇 建筑学
- 197 篇 动力工程及工程热...
- 185 篇 光学工程
- 166 篇 化学工程与技术
- 154 篇 土木工程
1,900 篇 理学
- 1,065 篇 数学
- 718 篇 生物学
- 442 篇 统计学（可授理学、...
- 285 篇 物理学
- 252 篇 系统科学
- 140 篇 化学
1,152 篇 管理学
- 656 篇 管理科学与工程(可...
- 582 篇 图书情报与档案管...
- 316 篇 工商管理
408 篇 医学
- 354 篇 临床医学
- 298 篇 基础医学(可授医学...
- 188 篇 药学(可授医学、理...
244 篇 教育学
- 243 篇 教育学
211 篇 法学
- 197 篇 社会学
119 篇 农学
111 篇 经济学
50 篇 文学
7 篇 艺术学
5 篇 军事学

主题

556 篇 machine learning
456 篇 deep learning
264 篇 training
253 篇 data mining
235 篇 data models
220 篇 feature extracti...
215 篇 accuracy
184 篇 support vector m...
178 篇 predictive model...
138 篇 neural networks
137 篇 machine learning...
130 篇 computational mo...
121 篇 reinforcement le...
107 篇 convolutional ne...
103 篇 real-time system...
93 篇 forecasting
90 篇 artificial intel...
89 篇 learning systems
87 篇 transfer learnin...
86 篇 big data

机构

69 篇 chitkara univers...
17 篇 school of electr...
15 篇 computer science...
14 篇 harbin engineeri...
13 篇 graphic era hill...
12 篇 building civil a...
12 篇 uttaranchal inst...
12 篇 computer science...
11 篇 university of ch...
10 篇 school of electr...
10 篇 school of comput...
10 篇 graphic era deem...
10 篇 school of electr...
10 篇 yonsei univ dept...
9 篇 wuhan university...
9 篇 univ chinese aca...
9 篇 school of inform...
8 篇 school of remote...
7 篇 university of sa...
7 篇 microsoft resear...

作者

17 篇 kukreja vinay
15 篇 vinay kukreja
13 篇 yin hujun
12 篇 liu yang
12 篇 corchado emilio
11 篇 mehta shiva
10 篇 shiva mehta
10 篇 hujun yin
10 篇 cho sung-bae
9 篇 notsu akira
9 篇 silva catarina
9 篇 alhajj reda
7 篇 ksieniewicz pawe...
7 篇 hammer barbara
7 篇 zhang byoung-tak
7 篇 wozniak michal
7 篇 hussain abir
7 篇 soubra hassan
7 篇 huang de-shuang
7 篇 camacho david

语言

6,794 篇 英文
352 篇 其他
28 篇 中文
1 篇 西班牙文
1 篇 俄文

检索条件"任意字段=11th International Conference on Intelligent Data Engineering and Automated Learning"

共 7157 条记录，以下是811-820 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

PARALLEL DEEP NEURAL NETWORKS HAVE ZERO DUALITY GAP 11

PARALLEL DEEP NEURAL NETWORKS HAVE ZERO DUALITY GAP

引用

11th international conference on learning Representations, ICLR 2023

作者： Wang, Yifei Ergen, Tolga Pilanci, Mert Department of Electrical Engineering Stanford University United States

Training deep neural networks is a challenging non-convex optimization problem. Recent work has proven that the strong duality holds (which means zero duality gap) for regularized finite-width two-layer ReLU networks and consequently provided an equivalent convex training problem. However, extending this result to deeper networks remains to be an open problem. In this paper, we prove that the duality gap for deeper linear networks with vector outputs is non-zero. In contrast, we show that the zero duality gap can be obtained by stacking standard deep networks in parallel, which we call a parallel architecture, and modifying the regularization. therefore, we prove the strong duality and existence of equivalent convex problems that enable globally optimal training of deep networks. As a by-product of our analysis, we demonstrate that the weight decay regularization on the network parameters explicitly encourages low-rank solutions via closed-form expressions. In addition, we show that strong duality holds for three-layer standard ReLU networks given rank-1 data matrices. © 2023 11th international conference on learning Representations, ICLR 2023. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Transfer learning Approach for Face Liveness Detection 11

A Transfer Learning Approach for Face Liveness Detection

引用

11th IEEE international conference on intelligent Computing and Information Systems, ICICIS 2023

作者： Omara, Mahmoud Fayez, Mahmoud Khalid, Heba Ghoniemy, Said Ain Shams University Faculty of Computer and Information Sciences Cairo Egypt

ISBN: (纸本)9798350322101

In the rapidly advancing domain of digital security, the authenticity of facial recognition systems remains essential. Face spoofing attacks pose a significant challenge, with malicious entities attempting to deceive facial authentication systems using counterfeit techniques. In this study, we present a novel transfer learning methodology leveraging the MoViNet model, renowned for its efficiency in video data processing, to discern genuine from spoofed faces. Our approach addresses the specific challenges of face liveness detection by fine-tuning the MoViNet model on a diverse dataset of both genuine and counterfeit face videos, enhanced by preprocessing steps such as frame extraction, padding, resizing, and normalization. this meticulous adaptation not only improves training but, through our transfer learning technique, equips the model with a robust defense against new and unseen spoofing attempts, ultimately achieving a notable zero False Acceptance Rate (FAR) - a testament to its high generalizability and uncompromising efficacy against spoofing. Post-training, our MoViNet-based model exhibited a remarkable accuracy of 98%, with a Precision of 1.0, an F1-Score of 0.94, and most notably, an Equal Error Rate (EER) and Half Total Error Rate (HTER) of 0.05%. When compared with several state-of-the-art methods, our approach not only matched but surpassed their efficacy. the findings underscore the potential of MoViNet in fortifying facial recognition systems against spoofing attacks, setting a new benchmark in the field, and offering robust protection for various real-world applications. We believe our transfer learning approach opens exciting possibilities for enhancing security and user experience in diverse domains. © 2023 IEEE.

关键词： learning systems

来源：评论

学校读者我要写书评

暂无评论

Confluence of Machine learning and Internet of things for E-Healthcare Security 8th

Confluence of Machine Learning and Internet of Things for E-...

引用

8th international conference on Microelectronics Electromagnetics and Telecommunications, ICMEET 2023

作者： Pattnayak, Parthasarathi Das, Tulip Mohanty, Arpeeta Patnaik, Sanghamitra School of Computer Applications KIIT Deemed to be University Odisha Bhubaneswar India Faculty of Emerging Technologies SRI SRI University Odisha Cuttack India School of Computer Applications KIIT Deemed to be University Odisha Bhubaneswar India School of Law KIIT Deemed to be University Odisha Bhubaneswar India

ISBN: (纸本)9789819784219

In the current era, the e-communication technology is developing swiftly and has made a remarkable transformation in e-healthcare sector by facilitating efficient and secure transmission of patient’s data. Internet of things (IoT) is developing drastically in the e-healthcare sector and the intelligent devices are also improving with many new innovative enhancements. the confluence of IoT and ML is manifested in many sectors but its implementation in e-healthcare sector provides real-time surveillance and monitoring of patient’s data and health status through prediction, anticipation and the capability of taking decisions intelligently. Nowadays, cryptographic and biometric systems, anomaly detection and machine learning (ML) approaches for authentication are being widely used for ensuring the security and functioning of healthcare systems. the present study aims to know how the convergence of IoT e-healthcare management system (EHMS) and ML techniques helps to design automated systems for proper monitoring and intelligent decision making. It also focuses to present an innovative architecture to safeguard the real-time healthcare from outside threats with the consumption of less possible resources of low-powered devices. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Precision Agriculture-Machine learning Based Approach 11

Precision Agriculture-Machine Learning Based Approach

引用

11th international conference on Internet of Everything, Microwave engineering, Communication and Networks, IEMECON 2023

作者： Mallikarjun, B.C. Gowd, V Yanjare Gagan, S. Vishwas, K.P. Gagan Kumar, L. Siddaganga Institute of Technology Dept. of Ete Karnataka state Tumkur India

ISBN: (纸本)9781665475129

In this paper Real-time use of precision agriculture with the help of IoT and Machine learning is demonstrated. the NodeMCU-ESP12E and other sensor networks has been used for monitoring and controlling smart irrigation system, which is simple in design and also cost-effective. It is advantageous for farmers to irrigate their land by the application of smart irrigation system. this smart irrigation system has Capacitive Soil moisture Sensor-v2.0, Temperature and Humidity sensor-DHT22, Rain drop Sensor. solenoid valves are used to control the water flow. data from the farm-field is sent to cloud by NodeMCU-ESP12E transmitter wirelessly. At the receiver side, based on the sensor data NodeMCU-ESP12E drives the 3-Phase motor starter. this enables the remote-control mechanism through an application. Users can control motor, sprinklers and solenoid valves through the *** paper also focuses on fertilizer recommendation system based on machine learning, the ML model takes the inputs such as soil moisture, temperature, humidity, soil type, crop type and N-P-K values to predict the suitable fertilizer which can be used for the respective farm-field. so that farm-field nutrition will be improved. © 2023 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

PRIVATE FEDERATED learning WIthOUT A TRUSTED SERVER: OPTIMAL ALGORIthMS FOR CONVEX LOSSES 11

PRIVATE FEDERATED LEARNING WITHOUT A TRUSTED SERVER: OPTIMAL...

引用

11th international conference on learning Representations, ICLR 2023

作者： Lowy, Andrew Razaviyayn, Meisam Department of Mathematics University of Southern California Los AngelesCA90089 United States Department of Industrial & Systems Engineering University of Southern California Los AngelesCA90089 United States

this paper studies federated learning (FL)-especially cross-silo FL-with data from people who do not trust the server or other silos. In this setting, each silo (e.g. hospital) has data from different people (e.g. patients) and must maintain the privacy of each person's data (e.g. medical record), even if the server or other silos act as adversarial eavesdroppers. this requirement motivates the study of Inter-Silo Record-Level Differential Privacy (ISRL-DP), which requires silo i's communications to satisfy record/item-level differential privacy (DP). ISRL-DP ensures that the data of each person (e.g. patient) in silo i (e.g. hospital i) cannot be leaked. ISRL-DP is different from well-studied privacy notions. Central and user-level DP assume that people trust the server/other silos. On the other end of the spectrum, local DP assumes that people do not trust anyone at all (even their own silo). Sitting between central and local DP, ISRL-DP makes the realistic assumption (in cross-silo FL) that people trust their own silo, but not the server or other silos. In this work, we provide tight (up to logarithms) upper and lower bounds for ISRL-DP FL with convex/strongly convex loss functions and homogeneous (i.i.d.) silo data. Remarkably, we show that similar bounds are attainable for smooth losses with arbitrary heterogeneous silo data distributions, via an accelerated ISRL-DP algorithm. We also provide tight upper and lower bounds for ISRL-DP federated empirical risk minimization, and use acceleration to attain the optimal bounds in fewer rounds of communication than the state-of-the-art. Finally, with a secure "shuffler" to anonymize silo messages (but without a trusted server), our algorithm attains the optimal central DP rates under more practical trust assumptions. Numerical experiments show favorable privacy-accuracy tradeoffs for our algorithm in classification and regression tasks. © 2023 11th international conference on learning Representations, ICLR 2023. All ri

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

Generating synthetic data on agricultural crops with DCGAN 11

Generating synthetic data on agricultural crops with DCGAN

引用

11th international conference on Advanced Informatics: Concept, theory and Application, ICAICTA 2024

作者： Pasaribu, Fieter Brain Dewi, Luh Joni Erawati Aryanto, Kadek Yota Ernanda Seputra, Ketut Agus Varnakovida, Pariwate Kertiasih, Ni Ketut Computer Science Universitas Pendidikan Ganesha Singaraja Indonesia Software Engineering Universitas Pendidikan Ganesha Singaraja Indonesia King Mongkut's University of Technology Faculty of Science Thonburi Thailand

ISBN: (纸本)9798331520311

Convolutional Neural Network (CNN) is one of the deep learning architectures that is very effective for handling images. CNN is able to automatically extract important features from images, making it very suitable for various image processing tasks such as classification, object detection, and segmentation. However, even though CNN has great capabilities, one important thing to note is the amount of data. A considerable amount of data is needed for the CNN model to work optimally and avoid overfitting. To handle this problem, a synthetic data augmentation process is used using the Deep Convolutional Generative Adversarial Network (DCGAN) method. the generator network contained in the DCGAN model has a latent space dimension input whose value can vary. the size of the latent space dimension is very important in enabling data or image reconstruction during the training process. this study tested latent space dimension values on a corn plant dataset totaling 9159. the latent space values used in this experiment were 64, 100, and 128. In addition, this study also tested different batch sizes, namely 64 and 128. the model was evaluated using Fre'chet Inception Distance (FID) and Inception Score (IS). From the evaluation results, the best score on FID was 0.018001 and IS 1.239421. the greater the latent space value, the more realistic and clear the image results will be. Likewise, the smaller the batch size value, the more realistic and clear the image results. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Deep Sequence Models for Time Series data: A Comparative Study and Parameter Fine-Tuning Approach 11

Deep Sequence Models for Time Series Data: A Comparative Stu...

引用

11th international conference on Electrical engineering, Computer Science and Informatics, EECSI 2024

作者： Arwansyah Suryani Sy, Hasyrif Faizal Alam, Samsu Piu, Sriwahyuningsih Usman Tamsir, Nurlindasari Djafar, Imran Dipa Makassar University Department of Informatics Makassar Indonesia

ISBN: (纸本)9798350355314

the modeling and prediction of time series data have become pivotal in data science and machine learning. Deep learning architectures, particularly Long Short-Term Memory (LSTM) networks, have proven effective in capturing complex temporal relationships, outperforming traditional methods. this study compares the performance of three LSTM variants-Convolutional LSTM (ConvLSTM), Bidirectional LSTM (BiLSTM), and Stacked LSTM-using datasets such as ETth, ETTm, Energy, AQI, and Exchange Rate. Each model is trained and tested on subsets of these datasets, with hyperparameters like the number of layers, neurons, learning rate, batch size, optimizer, and loss function fine-tuned for optimal performance. the models are evaluated using metrics like Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). Results indicate that ConvLSTM excels with spatiotemporal datasets, BiLSTM effectively captures full sequence contexts, and Stacked LSTM benefits from more in-depth representation. this research enhances the understanding of LSTM variants in time series analysis, demonstrating that fine-tuning can significantly boost performance. the findings apply to improving accuracy in time series forecasting across various fields. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Relationship Between Training data and Error in Tsunami Arrival Time Prediction Using Machine learning 11th

Relationship Between Training Data and Error in Tsunami Arri...

引用

11th international conference on Asian and Pacific Coasts, APAC 2023

作者： Gunji, Kota Tsuzuki, Tatsuya Honda, Shiho Arikawa, Taro Chuo University Tokyo Japan

ISBN: (纸本)9789819974085

It is important to predict a tsunami immediately after an earthquake has occurred, and it is also important to know the prediction error in advance. In this study, a neural network (NN) capable of instantaneous prediction by learning the input and output relationship in advance was used to predict the tsunami arrival time from the initial water level immediately after an earthquake has taken place. A total of 2,400 data sets were examined, and NN models were created for each earthquake scale considering the variation of the data. As a result, the errors were different for each earthquake scale and number of data, and the overestimation and underestimation differed in the three target regions considered. For the proposed model, variation in the output of the training data has a large impact on the prediction results. thus, when the variation doubles, more than twice training data are necessary to achieve the same accuracy. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

thE SURPRISING COMPUTATIONAL POWER OF NONDETERMINISTIC STACK RNNS 11

THE SURPRISING COMPUTATIONAL POWER OF NONDETERMINISTIC STACK...

引用

11th international conference on learning Representations, ICLR 2023

作者： DuSell, Brian Chiang, David Department of Computer Science and Engineering University of Notre Dame United States

Traditional recurrent neural networks (RNNs) have a fixed, finite number of memory cells. In theory (assuming bounded range and precision), this limits their formal language recognition power to regular languages, and in practice, RNNs have been shown to be unable to learn many context-free languages (CFLs). In order to expand the class of languages RNNs recognize, prior work has augmented RNNs with a nondeterministic stack data structure, putting them on par with pushdown automata and increasing their language recognition power to CFLs. Nondeterminism is needed for recognizing all CFLs (not just deterministic CFLs), but in this paper, we show that nondeterminism and the neural controller interact to produce two more unexpected abilities. First, the nondeterministic stack RNN can recognize not only CFLs, but also many non-context-free languages. Second, it can recognize languages with much larger alphabet sizes than one might expect given the size of its stack alphabet. Finally, to increase the information capacity in the stack and allow it to solve more complicated tasks with large alphabet sizes, we propose a new version of the nondeterministic stack that simulates stacks of vectors rather than discrete symbols. We demonstrate perplexity improvements with this new model on the Penn Treebank language modeling benchmark. © 2023 11th international conference on learning Representations, ICLR 2023. All rights reserved.

关键词： Context free languages

来源：评论

学校读者我要写书评

暂无评论

AI for Safer Streets: Deep learning-Based Road Accident Detection from Video Footage 4

AI for Safer Streets: Deep Learning-Based Road Accident Dete...

引用

4th international conference on intelligent Technologies, CONIT 2024

作者： Singh, Retinderdeep Sharma, Neha Rajput, Kapil Kumar, Mukesh Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Computer Science & Engineering Uttarakhand Dehradun248002 India

ISBN: (纸本)9798350349900

the detection of road accidents is of great concern across the world. To put a stop to all the tragedy that ensues, we need efficient and workable monitoring and detection systems. In this paper, results for recognizing road accidents through the analysis of a holistic image database from camera surveillance with balanced classes are presented. 19 layers of Convolutional Neural Network (CNN) designed in the light is also built and trained on these images for accurate accident detection. When trained, the model exhibits robust learning capacity and its training or validation accuracy nigh reached 9 4% and 9 7. 6 7%, a great achievement. this suggests that it can generalize well to capture key features indicative of road accidents in CCTV footage. After the training stage is complete, the model is tested on a separate test dataset where it struts its stuff and achieves an impressive test accuracy of 9 8%. this high degree of accuracy means that it can accurately recognize road accidents from CCTV images, which is critical for prompt response and amelioration measures. In addition, the model's Receiver Operating Characteristic (ROC) analysis presents some data: recovered in ROC values - 0.92 for accident class and 0.87 for other classes (non-accident instances). this further testifies to the model's capacity in real-world accident detection situations as well as its unambiguity among different types of accidents. Overall, our study illustrates the effectiveness of deep-learning technology applied to the road accident detection such as a 19-layer CNN model. Consistent high accuracy rates and robust ROC values are indicators that show great promise for how widely it might ultimately be used to enhance safety on our roads through automated accident detection systems. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 78 79 80 81 82 83 84 85 86 87 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：